skills.rest
himes19
himes19COMMUNITY
Explore all skills by this author →
GitHub

audio-transcription

Transcribe audio recordings into speaker-labeled transcripts with Deepgram Nova-2.

Updated Apr 12, 2026
Search Tags:#sales#crm#transcription#nlp#audio#deepgram#diarization
One-click install
npx skills add https://github.com/himes19/pulsevolt-infra --skill audio-transcription-himes19
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: audio-transcription
Source: https://github.com/himes19/pulsevolt-infra/tree/main/skills/audio-transcription
Command: npx skills add https://github.com/himes19/pulsevolt-infra --skill audio-transcription-himes19

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires node, curl, and includes scripts (resource) components.

What problem does it solve?

Transcribing audio is time-consuming and error-prone. This skill provides automated, speaker-labeled transcripts to accelerate insights for sales and CRM workflows.

Core Features & Use Cases

  • Speaker diarization to attribute who spoke when
  • Multilingual support (Spanish and English) with easy switching
  • Outputs include structured transcripts and a plain text version for AI processing
  • Integrates into CRM workflows to surface deals, contacts, and actions

Quick Start

Transcribe an audio file using transcribe.sh and convert the result with parse-deepgram.sh to obtain both JSON and plain-text transcripts.

Frequently Asked Questions about audio-transcription

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I transcribe sales call recordings with speaker diarization?▼

This skill transcribes audio recordings with speaker diarization using the Deepgram Nova-2 API, attributing speech to specific speakers and outputting structured JSON with metadata for CRM workflows.

Does Deepgram transcription support Spanish and English audio files?▼

Yes, Deepgram transcription supports both Spanish and English audio files. You can configure the language setting to easily switch between them for accurate, punctuated transcripts of voice notes or meetings.

How do I convert Deepgram JSON output into plain text for AI processing?▼

You convert Deepgram JSON output into plain text using the parse-deepgram.sh script, which extracts a clean transcript version ready for AI processing and downstream CRM integration.

What do I need to run automated audio transcription scripts locally?▼

You need Node.js and curl installed locally to execute the automated audio transcription scripts, which handle API requests to Deepgram and process the resulting JSON output.

Can I integrate speaker-labeled transcripts directly into CRM workflows?▼

Yes, you can integrate speaker-labeled transcripts into CRM workflows. The structured JSON and plain text outputs are designed to surface deals, contacts, and actions directly from your sales call audio.

Related Skills

Explore More Marketing & Sales Skills→
jacob-splitjacob-split

minutes-setup

Guide first-time Minutes users through hosted configuration and cloud transcription setup.

Community
Advanced
ericwang915ericwang915
38

pdf_reader

Extract text and metadata from PDFs using PyPDF2.

Community
Intermediate
BeltDoorBeltDoor

speaker-id

Relabels incorrect transcript speakers using content-based mapping and ambiguity flags.

Community
Advanced
fikriaffikriaf

vibevoice

Transcribe speech to text with speaker diarization and multilingual support.

Community
Intermediate